TLSA_DataExploration
Yu-Hsuan Chou
2021/8/6
library(data.table)
library(ggplot2)
library(fixest)## fixest 0.9.0, BREAKING changes! (Permanently remove this message with fixest_startup_msg(FALSE).)
## - In i():
## + the first two arguments have been swapped! Now it's i(factor_var, continuous_var) for interactions.
## + argument 'drop' has been removed (put everything in 'ref' now).
## - In feglm():
## + the default family becomes 'gaussian' to be in line with glm(). Hence, for Poisson estimations, please use fepois() instead.library(ggfortify)
library(stargazer)##
## Please cite as:## Hlavac, Marek (2018). stargazer: Well-Formatted Regression and Summary Statistics Tables.## R package version 5.2.2. https://CRAN.R-project.org/package=stargazerlibrary(stringr)subject.dt <- as.data.table(read.csv("/Users/hsiao/Desktop/Projects/HRS_Chao/LTC_TSLA/main_subject_0820.csv"))
fmlymmb.dt <- as.data.table(read.csv("/Users/hsiao/Desktop/Projects/HRS_Chao/LTC_TSLA/family_member_1005.csv"))# what happened on augmented spouses
# Chou miscoded. She used the qser_no for all subjects over multiple observed years
# After change of the code, 405 problematic remains, while 326 of them is NAs, therefore can be omited.
# NA are mainnly other relationship in 1996 which should be omitted earlier
# the 79 remaining is mainly consisted of 同居老伴 ( 1993, 1996 old 沒有問同居)
#
# spou<- fmlymmb.dt[relationship ==2 & ObsPartnerY ==0]
# sum(is.na(spou$marstat)) # 326
# spou<- spou[! is.na(marstat)]
# who <- fmlymmb.dt[ ObsPartnerY ==0 & relationship ==2 & is.na(marstat)]
# table(who)# duplicated people
# main change :
# detected_1 added to detect if one fam member only exist in specific year, is he the only one ?
# otherwise he will go through k_grouping.
# unif stands for the unificated code
# test<- copy(fmlymmb.dt)
# sum(duplicated(test$unif))Family Member Personalities
Preprocess
fmlymmb.dt$gender = ifelse(fmlymmb.dt$gender == 1, 1, 0) # gender 0 = females
fmlymmb.dt$partner = ifelse(fmlymmb.dt$relationship == 2, 1, 0)
fmlymmb.dt$working = ifelse(fmlymmb.dt$work == 1, 1, 0)
fmlymmb.dt$unmarried = ifelse(fmlymmb.dt$marstat == 6, 1, 0)
fmlymmb.dt$attend_at_least_uni = ifelse(fmlymmb.dt$edu >= 13, 1, 0)
fmlymmb.dt$attend_at_least_high_school = ifelse(fmlymmb.dt$edu >=10, 1, 0)
# age above 15 & unmarry -> 6, if under 15 -> NA
fmlymmb.dt$livTogether = ifelse(fmlymmb.dt$livstat == 0, 1, 0)
fmlymmb.dt$primaryADL = ifelse(fmlymmb.dt$adl_who_help == fmlymmb.dt$relationship, 1, 0)
fmlymmb.dt$primaryIADL = ifelse(fmlymmb.dt$iadl_who_help ==
fmlymmb.dt$relationship, 1, 0)
fmlymmb.dt$fmNeedADL = ifelse(! is.na(fmlymmb.dt$adl_who_help) , 1, 0)
fmlymmb.dt$fmNeedIADL = ifelse(! is.na(fmlymmb.dt$iadl_who_help) , 1, 0)
fmlymmb.dt$subject_residency = as.character(fmlymmb.dt$subject_residency)
# Define degree of intimacysubject.dt[, y_qser_no := paste0( survey_year, qser_no)]
fmlymmb.dt[, y_qser_no := paste0(survey_year, qser_no)]
non_married.obs <- subject.dt[marstat == 0]$y_qser_no
fmlymmb.dt.nmar <- fmlymmb.dt[y_qser_no %in% non_married.obs]
fmlymmb.dt$ObsPartnerY <- ifelse(fmlymmb.dt$y_qser_no %in% non_married.obs, 0, 1)
# fmlymmb.dt<- fmlymmb.dt[! (ObsPartnerY ==0 & relationship ==2 & is.na(marstat))]Merging with Subject Data
subject.dt$rsex = ifelse(subject.dt$rsex == 1, 1, 0)
fmlymmb.dt <- merge(fmlymmb.dt,
subject.dt[,c("qser_no", "rsex", "survey_year", "rage")],
all.x = TRUE,
by = c("qser_no", "survey_year"))Summary
fm.with.need <- fmlymmb.dt[fmNeedADL == 1]
fm.primary.c <- fmlymmb.dt[primaryADL == 1]
fm.whot.need <- fmlymmb.dt[fmNeedADL == 0]
print(paste("People in families with need:", nrow(fm.with.need)))## [1] "People in families with need: 8838"print(paste("Number of Primary Caregiver:", nrow(fm.primary.c)))## [1] "Number of Primary Caregiver: 997"print(paste("People in families without need:", nrow(fm.whot.need)))## [1] "People in families without need: 106317"Age, Gender, Education, Marriage Status
rbind(fm.with.need[ObsPartnerY == 1,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE)
)],
fm.with.need[ObsPartnerY == 0,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE)
)],
fm.whot.need[ObsPartnerY == 1,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE)
)],
fm.whot.need[ObsPartnerY == 0,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE)
)],
fm.primary.c[ObsPartnerY == 1,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE)
)],
fm.primary.c[ObsPartnerY == 0,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE)
)])## AGE EDU SEX PARTNER WORK UNMARRIED LVTOGETER
## 1: 44.86280 8.867423 0.4691261 0.150887574 0.5494908 0.14773680 0.4866838
## 2: 46.98345 9.011438 0.4631104 0.001857749 0.5700219 0.12334554 0.4167553
## 3: 40.01084 9.916187 0.4649134 0.170294387 0.5924159 0.20870854 0.5226831
## 4: 40.50267 9.666419 0.4777033 0.003217158 0.6164537 0.16943892 0.4348839
## 5: 57.21417 5.964646 0.2811448 0.602693603 0.3384354 0.08080808 0.9528620
## 6: 46.44000 8.535980 0.2431762 0.004962779 0.5298507 0.14214464 0.9131514
## SUBSEX SUBAGE
## 1: 0.5461538 74.68426
## 2: 0.2324841 80.72853
## 3: 0.5724889 67.36235
## 4: 0.3024129 73.17677
## 5: 0.5690236 74.40587
## 6: 0.2183623 81.41687Regression
Families with need
fm.with.need$SubSameSex <- ifelse(fm.with.need$gender == fm.with.need$rsex, 1, 0)
need.reg1 <- feols(primaryADL ~ gender| survey_year, fm.with.need)## NOTE: 1 observation removed because of NA values (RHS: 1).need.reg2 <- feols(primaryADL ~ gender + age + age**2 | survey_year, fm.with.need)## NOTE: 42 observations removed because of NA values (RHS: 42).need.reg3 <- feols(primaryADL ~ gender + age + age**2 + edu | survey_year, fm.with.need)## NOTE: 275 observations removed because of NA values (RHS: 275).need.reg4 <- feols(primaryADL ~ gender + age + age**2 + edu + working | survey_year, fm.with.need)## NOTE: 313 observations removed because of NA values (RHS: 313).need.reg5 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried | survey_year, fm.with.need)## NOTE: 590 observations removed because of NA values (RHS: 590).need.reg6 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex | survey_year, fm.with.need)## NOTE: 590 observations removed because of NA values (RHS: 590).need.reg7 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex + partner | survey_year, fm.with.need)## NOTE: 590 observations removed because of NA values (RHS: 590).need.reg8 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex + partner + livTogether | survey_year, fm.with.need)## NOTE: 596 observations removed because of NA values (RHS: 596).need.reg9 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex + partner + livTogether + subject_in_nursing_house | survey_year, fm.with.need)## NOTE: 596 observations removed because of NA values (RHS: 596).need.reg10 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex + partner + livTogether | survey_year, fm.with.need[ subject_in_nursing_house ==0])## NOTE: 590 observations removed because of NA values (RHS: 590).etable(need.reg1, need.reg2, need.reg3, need.reg4, need.reg5, need.reg6, need.reg7, need.reg7, need.reg8, need.reg10)## need.reg1 need.reg2 need.reg3
## Dependent Var.: primaryADL primaryADL primaryADL
##
## gender -0.0910*** (0.0087) -0.0926*** (0.0099) -0.0862*** (0.0095)
## age -0.0010 (0.0006) -0.0010 (0.0011)
## age square 4.36e-5** (7.04e-6) 3.56e-5** (5.35e-6)
## edu -0.0059** (0.0009)
## working
## unmarried
## SubSameSex
## partner
## livTogether
## Fixed-Effects: ------------------- ------------------- -------------------
## survey_year Yes Yes Yes
## _______________ ___________________ ___________________ ___________________
## S.E.: Clustered by: survey_year by: survey_year by: survey_year
## Observations 8,837 8,796 8,563
## R2 0.02120 0.04737 0.05087
## Within R2 0.02061 0.04683 0.05042
## need.reg4 need.reg5 need.reg6
## Dependent Var.: primaryADL primaryADL primaryADL
##
## gender -0.0851** (0.0148) -0.0851** (0.0128) -0.0869** (0.0144)
## age -0.0010 (0.0019) -0.0050 (0.0042) -0.0049 (0.0041)
## age square 3.48e-5* (1.19e-5) 6.86e-5. (2.99e-5) 6.69e-5. (2.91e-5)
## edu -0.0058** (0.0011) -0.0074* (0.0017) -0.0075* (0.0016)
## working -0.0026 (0.0214) -0.0030 (0.0196) -0.0030 (0.0195)
## unmarried 0.0124 (0.0139) 0.0135 (0.0140)
## SubSameSex -0.0094 (0.0089)
## partner
## livTogether
## Fixed-Effects: ------------------ ------------------ ------------------
## survey_year Yes Yes Yes
## _______________ __________________ __________________ __________________
## S.E.: Clustered by: survey_year by: survey_year by: survey_year
## Observations 8,525 8,248 8,248
## R2 0.04969 0.05171 0.05191
## Within R2 0.04934 0.05137 0.05157
## need.reg7 need.reg7 need.reg8
## Dependent Var.: primaryADL primaryADL primaryADL
##
## gender -0.0699** (0.0115) -0.0699** (0.0115) -0.0755** (0.0093)
## age 0.0070 (0.0045) 0.0070 (0.0045) 0.0158* (0.0039)
## age square -9.22e-5. (3.83e-5) -9.22e-5. (3.83e-5) -0.0002** (3.45e-5)
## edu -0.0041. (0.0018) -0.0041. (0.0018) -0.0028 (0.0016)
## working 0.0055 (0.0135) 0.0055 (0.0135) 0.0004 (0.0100)
## unmarried 0.0223 (0.0110) 0.0223 (0.0110) -0.0264. (0.0115)
## SubSameSex 0.0481* (0.0115) 0.0481* (0.0115) 0.0450* (0.0114)
## partner 0.4775*** (0.0446) 0.4775*** (0.0446) 0.3356** (0.0458)
## livTogether 0.2324*** (0.0125)
## Fixed-Effects: ------------------- ------------------- -------------------
## survey_year Yes Yes Yes
## _______________ ___________________ ___________________ ___________________
## S.E.: Clustered by: survey_year by: survey_year by: survey_year
## Observations 8,248 8,248 8,242
## R2 0.14906 0.14906 0.24413
## Within R2 0.14875 0.14875 0.24385
## need.reg10
## Dependent Var.: primaryADL
##
## gender -0.0831** (0.0116)
## age 0.0165* (0.0040)
## age square -0.0002** (3.49e-5)
## edu -0.0033 (0.0018)
## working -1.38e-5 (0.0106)
## unmarried -0.0208 (0.0129)
## SubSameSex 0.0487* (0.0110)
## partner 0.3646** (0.0424)
## livTogether 0.2289*** (0.0125)
## Fixed-Effects: -------------------
## survey_year Yes
## _______________ ___________________
## S.E.: Clustered by: survey_year
## Observations 7,607
## R2 0.24881
## Within R2 0.24851Decision Tree
library(rpart)
library(rpart.plot)simple.tree <- rpart(primaryADL ~ gender + age + age**2 +
edu + partner + working + SubSameSex +
unmarried + livTogether, data = fm.with.need, cp=.008)
rpart.plot(simple.tree, faclen=0,
box.palette="RdBu",
fallen.leaves=TRUE,
shadow.col="gray",
nn=TRUE)
simple.tree <- rpart(primaryADL ~ gender + age + age**2 +
edu + partner + working + SubSameSex +
unmarried, data = fm.with.need, cp=.003)
rpart.plot(simple.tree, faclen=0,
box.palette="RdBu",
fallen.leaves=TRUE,
shadow.col="gray",
nn=TRUE)
simple.tree <- rpart(primaryADL ~ gender + age + age**2 +
edu + working + SubSameSex +
unmarried, data = fm.with.need, cp=.003)
rpart.plot(simple.tree, faclen=0,
box.palette="RdBu",
fallen.leaves=TRUE,
shadow.col="gray",
nn=TRUE)
# which spouse would be the main giver
## omitted some very important variables : partner income, partner health status
simple.tree <- rpart(primaryADL ~ gender + age + age**2 +
edu + working + SubSameSex +
unmarried, data = fm.with.need[ partner ==1 ], cp=.003)
rpart.plot(simple.tree, faclen=0,
box.palette="RdBu",
fallen.leaves=TRUE,
shadow.col="gray",
nn=TRUE)
PCA Clustering
data.pca <- fm.with.need[,c("gender", "age", "edu", "working", "unmarried", "SubSameSex", "partner", "primaryADL")]
data.pca$primaryADL <- factor(data.pca$primaryADL)
simple.pca <- prcomp(formula = ~ .,
data = data.pca[,1:7],
scale = TRUE)
# take away livtogetherplot(simple.pca, type="line")
abline(h=1, col="blue")
simple.pca$rotation[,1:3]## PC1 PC2 PC3
## gender -0.1387858 0.6613955 -0.057681467
## age 0.5284127 0.1662838 0.229305578
## edu -0.4666603 0.1445338 0.004934944
## working -0.3486703 0.4194933 0.401354192
## unmarried -0.3174198 -0.1157329 -0.737809873
## SubSameSex -0.1833693 -0.5437932 0.367102949
## partner 0.4772798 0.1701055 -0.322264293first.pca <- simple.pca$rotation[, 1] # 第一主成份
second.pca <- simple.pca$rotation[, 2] # 第二主成份
third.pca <- simple.pca$rotation[, 3] # 第三主成份
dotchart(first.pca[order(first.pca, decreasing=FALSE)] , # 排序後的係數
main="Loading Plot for PC1", # 主標題
xlab="Variable Loadings", # x軸的標題
col="black")
dotchart(second.pca[order(second.pca, decreasing=FALSE)] , # 排序後的係數
main="Loading Plot for PC2", # 主標題
xlab="Variable Loadings", # x軸的標題
col="black")
dotchart(third.pca[order(third.pca, decreasing=FALSE)] , # 排序後的係數
main="Loading Plot for PC3", # 主標題
xlab="Variable Loadings", # x軸的標題
col="black")
library(devtools)## 載入需要的套件：usethisinstall_github('sinhrks/ggfortify')## Skipping install of 'ggfortify' from a github remote, the SHA1 (195b1fb1) has not changed since last install.
## Use `force = TRUE` to force installationlibrary(ggfortify); library(ggplot2)
autoplot(simple.pca, data = data.pca, colour = 'primaryADL', alpha=0.1, loadings = TRUE, loadings.colour = 'gray', loadings.label = TRUE, loadings.label.alpha = 0.4, loadings.label.colour = "black")## Warning in as.data.table.list(x, keep.rownames = keep.rownames, check.names =
## check.names, : Item 2 has 8248 rows but longest item has 8838; recycled with
## remainder.
Excluding Married Observations
Summary
Clean Those with Partners
fmlymmb.dt.nmar <- fmlymmb.dt[ObsPartnerY == 0]
odd.obs <- unique(fmlymmb.dt.nmar[relationship==2]$qser_no) # 同居但沒結婚 72
fmlymmb.dt.nmar <- fmlymmb.dt.nmar[!(fmlymmb.dt.nmar$qser_no %in% odd.obs)]
table(fmlymmb.dt.nmar$relationship)##
## 3 9 10 11 12 13 14 15 16 17 18 19 21 22 23 24
## 3 1 1 37 102 7 22 1 4 2 2 2 82 25 6 4
## 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42
## 42 3 12 158 4019 2967 1604 771 398 12 162 2 52 95 3691 2438
## 43 44 45 46 47 49 50 51 52 53 54 59 61 62 70 72
## 1383 714 386 13 248 55 1 1427 1073 245 78 161 351 9 38 56
## 73 76 77 78 79 81 91 92 93 94 95 96 97
## 99 1 17 1 78 2 1185 655 375 143 79 1 2# fmlymmb.dt.nmar<- fmlymmb.dt.nmar[ relationship %in% c()]fm.with.need <- fmlymmb.dt.nmar[fmNeedADL == 1]
fm.primary.c <- fmlymmb.dt.nmar[primaryADL == 1]
fm.whot.need <- fmlymmb.dt.nmar[fmNeedADL == 0]
print(paste("People in families with need:", nrow(fm.with.need)))## [1] "People in families with need: 3713"print(paste("Number of Primary Caregiver:", nrow(fm.primary.c)))## [1] "Number of Primary Caregiver: 400"print(paste("People in families without need:", nrow(fm.whot.need)))## [1] "People in families without need: 21890"Age, Gender, Education, Marriage Status
rbind(fm.with.need[,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE),
Sub_in_nursing = mean( subject_in_nursing_house, na.rm = TRUE)
)],
fm.whot.need[,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE),
Sub_in_nursing = mean( subject_in_nursing_house, na.rm = TRUE)
)],
fm.primary.c[,.(AGE = mean(age, na.rm = TRUE),
EDU = mean(edu, na.rm = TRUE),
SEX = mean(gender, na.rm = TRUE),
PARTNER = mean(partner, na.rm = TRUE),
WORK = mean(working, na.rm = TRUE),
UNMARRIED = mean(unmarried, na.rm = TRUE),
LVTOGETER = mean(livTogether, na.rm = TRUE),
SUBSEX = mean(rsex, na.rm = TRUE),
SUBAGE = mean(rage, na.rm = TRUE),
Sub_in_nursing = mean( subject_in_nursing_house, na.rm = TRUE)
)])## AGE EDU SEX PARTNER WORK UNMARRIED LVTOGETER SUBSEX
## 1: 47.00108 8.996959 0.4651225 0 0.5703971 0.1215675 0.4197031 0.2267708
## 2: 40.50402 9.669533 0.4783463 0 0.6183188 0.1693116 0.4349837 0.2957515
## 3: 46.36524 8.570000 0.2450000 0 0.5288221 0.1407035 0.9125000 0.2125000
## SUBAGE Sub_in_nursing
## 1: 80.82758 0.105844331
## 2: 73.28595 0.002832344
## 3: 81.40000 0.010000000Regression
Family with Need (Observations Not Having Partners)
fm.with.need$SubSameSex <- ifelse(fm.with.need$gender == fm.with.need$rsex, 1, 0)
need.reg1 <- feols(primaryADL ~ gender| survey_year, fm.with.need)
need.reg2 <- feols(primaryADL ~ gender + age + age**2 | survey_year, fm.with.need)## NOTE: 22 observations removed because of NA values (RHS: 22).need.reg3 <- feols(primaryADL ~ gender + age + age**2 + edu | survey_year, fm.with.need)## NOTE: 118 observations removed because of NA values (RHS: 118).need.reg4 <- feols(primaryADL ~ gender + age + age**2 + edu + working | survey_year, fm.with.need)## NOTE: 133 observations removed because of NA values (RHS: 133).need.reg5 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried | survey_year, fm.with.need)## NOTE: 252 observations removed because of NA values (RHS: 252).need.reg6 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex | survey_year, fm.with.need)## NOTE: 252 observations removed because of NA values (RHS: 252).need.reg7 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex + livTogether | survey_year, fm.with.need)## NOTE: 257 observations removed because of NA values (RHS: 257).need.reg8 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex + livTogether | survey_year, fm.with.need)## NOTE: 257 observations removed because of NA values (RHS: 257).need.reg9 <- feols(primaryADL ~ gender + age + age**2 + edu + working + unmarried + SubSameSex + livTogether + subject_in_nursing_house + subject_residency | survey_year, fm.with.need)## NOTE: 257 observations removed because of NA values (RHS: 257).need.reg10 <- feols(primaryADL ~ gender + age + age**2 + attend_at_least_high_school + working + unmarried + SubSameSex + livTogether + subject_in_nursing_house + subject_residency | survey_year, fm.with.need)## NOTE: 257 observations removed because of NA values (RHS: 257).need.reg11 <- feols(primaryADL ~ gender + age + age**2 + attend_at_least_uni + working + unmarried + SubSameSex + livTogether + subject_in_nursing_house + subject_residency | survey_year, fm.with.need)## NOTE: 257 observations removed because of NA values (RHS: 257).etable(need.reg1, need.reg2, need.reg3, need.reg4, need.reg5, need.reg6, need.reg7, need.reg8, need.reg9, need.reg10, need.reg11)## need.reg1 need.reg2
## Dependent Var.: primaryADL primaryADL
##
## gender -0.0954** (0.0142) -0.0932** (0.0139)
## age 0.0056** (0.0009)
## age square -7.39e-5** (1.42e-5)
## edu
## working
## unmarried
## SubSameSex
## livTogether
## subject_in_nursing_house
## subject_residency10
## subject_residency11
## subject_residency12
## subject_residency13
## subject_residency14
## subject_residency15
## subject_residency16
## subject_residency17
## subject_residency18
## subject_residency19
## subject_residency2
## subject_residency20
## subject_residency21
## subject_residency22
## subject_residency3
## subject_residency4
## subject_residency5
## subject_residency6
## subject_residency7
## subject_residency8
## subject_residency9
## attend_at_least_high_school
## attend_at_least_uni
## Fixed-Effects: ------------------ --------------------
## survey_year Yes Yes
## ___________________________ __________________ ____________________
## S.E.: Clustered by: survey_year by: survey_year
## Observations 3,713 3,691
## R2 0.02374 0.03123
## Within R2 0.02353 0.03106
## need.reg3 need.reg4
## Dependent Var.: primaryADL primaryADL
##
## gender -0.0896** (0.0139) -0.0891** (0.0176)
## age 0.0055* (0.0014) 0.0055* (0.0019)
## age square -7.78e-5** (1.33e-5) -7.78e-5* (1.71e-5)
## edu -0.0037** (0.0005) -0.0036** (0.0005)
## working -0.0002 (0.0135)
## unmarried
## SubSameSex
## livTogether
## subject_in_nursing_house
## subject_residency10
## subject_residency11
## subject_residency12
## subject_residency13
## subject_residency14
## subject_residency15
## subject_residency16
## subject_residency17
## subject_residency18
## subject_residency19
## subject_residency2
## subject_residency20
## subject_residency21
## subject_residency22
## subject_residency3
## subject_residency4
## subject_residency5
## subject_residency6
## subject_residency7
## subject_residency8
## subject_residency9
## attend_at_least_high_school
## attend_at_least_uni
## Fixed-Effects: -------------------- -------------------
## survey_year Yes Yes
## ___________________________ ____________________ ___________________
## S.E.: Clustered by: survey_year by: survey_year
## Observations 3,595 3,580
## R2 0.03121 0.03102
## Within R2 0.03109 0.03086
## need.reg5 need.reg6
## Dependent Var.: primaryADL primaryADL
##
## gender -0.0859** (0.0165) -0.0493. (0.0226)
## age -0.0003 (0.0045) 0.0001 (0.0044)
## age square -2.68e-5 (3.76e-5) -3.22e-5 (3.68e-5)
## edu -0.0049** (0.0008) -0.0048** (0.0008)
## working -0.0019 (0.0123) -0.0030 (0.0121)
## unmarried -0.0039 (0.0112) -0.0085 (0.0133)
## SubSameSex 0.0664* (0.0199)
## livTogether
## subject_in_nursing_house
## subject_residency10
## subject_residency11
## subject_residency12
## subject_residency13
## subject_residency14
## subject_residency15
## subject_residency16
## subject_residency17
## subject_residency18
## subject_residency19
## subject_residency2
## subject_residency20
## subject_residency21
## subject_residency22
## subject_residency3
## subject_residency4
## subject_residency5
## subject_residency6
## subject_residency7
## subject_residency8
## subject_residency9
## attend_at_least_high_school
## attend_at_least_uni
## Fixed-Effects: ------------------ ------------------
## survey_year Yes Yes
## ___________________________ __________________ __________________
## S.E.: Clustered by: survey_year by: survey_year
## Observations 3,461 3,461
## R2 0.03310 0.04071
## Within R2 0.03301 0.04062
## need.reg7 need.reg8
## Dependent Var.: primaryADL primaryADL
##
## gender -0.0561* (0.0192) -0.0561* (0.0192)
## age 0.0153* (0.0045) 0.0153* (0.0045)
## age square -0.0002* (3.95e-5) -0.0002* (3.95e-5)
## edu -0.0035. (0.0015) -0.0035. (0.0015)
## working -0.0136 (0.0100) -0.0136 (0.0100)
## unmarried -0.0473* (0.0132) -0.0473* (0.0132)
## SubSameSex 0.0594* (0.0209) 0.0594* (0.0209)
## livTogether 0.2827*** (0.0021) 0.2827*** (0.0021)
## subject_in_nursing_house
## subject_residency10
## subject_residency11
## subject_residency12
## subject_residency13
## subject_residency14
## subject_residency15
## subject_residency16
## subject_residency17
## subject_residency18
## subject_residency19
## subject_residency2
## subject_residency20
## subject_residency21
## subject_residency22
## subject_residency3
## subject_residency4
## subject_residency5
## subject_residency6
## subject_residency7
## subject_residency8
## subject_residency9
## attend_at_least_high_school
## attend_at_least_uni
## Fixed-Effects: ------------------ ------------------
## survey_year Yes Yes
## ___________________________ __________________ __________________
## S.E.: Clustered by: survey_year by: survey_year
## Observations 3,456 3,456
## R2 0.19913 0.19913
## Within R2 0.19906 0.19906
## need.reg9 need.reg10
## Dependent Var.: primaryADL primaryADL
##
## gender -0.0555* (0.0178) -0.0548* (0.0184)
## age 0.0146* (0.0044) 0.0141* (0.0043)
## age square -0.0002* (3.65e-5) -0.0002* (3.62e-5)
## edu -0.0039. (0.0018)
## working -0.0115 (0.0096) -0.0088 (0.0096)
## unmarried -0.0555* (0.0130) -0.0524* (0.0126)
## SubSameSex 0.0577* (0.0199) 0.0579* (0.0203)
## livTogether 0.2791*** (0.0043) 0.2793*** (0.0040)
## subject_in_nursing_house -0.0236 (0.0178) -0.0225 (0.0184)
## subject_residency10 0.0653** (0.0079) 0.0723** (0.0093)
## subject_residency11 -0.0357 (0.0213) -0.0331 (0.0225)
## subject_residency12 -0.0294. (0.0137) -0.0307 (0.0147)
## subject_residency13 0.0071 (0.0378) 0.0072 (0.0406)
## subject_residency14 0.0248 (0.0127) 0.0246 (0.0125)
## subject_residency15 -0.0022 (0.0185) 7.11e-5 (0.0176)
## subject_residency16 -0.0069 (0.0253) -0.0080 (0.0237)
## subject_residency17 0.0265*** (0.0029) 0.0233** (0.0041)
## subject_residency18 -0.0351 (0.0305) -0.0372 (0.0304)
## subject_residency19 -0.0279* (0.0061) -0.0283** (0.0059)
## subject_residency2 -0.0360 (0.0178) -0.0292 (0.0152)
## subject_residency20 0.0257 (0.0325) 0.0265 (0.0313)
## subject_residency21 -0.0399 (0.0291) -0.0446 (0.0294)
## subject_residency22 0.0046 (0.0344) -0.0005 (0.0341)
## subject_residency3 0.0019 (0.0228) 0.0014 (0.0218)
## subject_residency4 -0.0607 (0.0756) -0.0674 (0.0730)
## subject_residency5 0.0262 (0.0277) 0.0265 (0.0288)
## subject_residency6 0.0640 (0.0512) 0.0678 (0.0502)
## subject_residency7 0.0102 (0.0126) 0.0085 (0.0133)
## subject_residency8 -0.0106 (0.0060) -0.0126. (0.0050)
## subject_residency9 -0.0224 (0.0150) -0.0208 (0.0140)
## attend_at_least_high_school -0.0559* (0.0152)
## attend_at_least_uni
## Fixed-Effects: ------------------ ------------------
## survey_year Yes Yes
## ___________________________ __________________ __________________
## S.E.: Clustered by: survey_year by: survey_year
## Observations 3,456 3,456
## R2 0.20424 0.20851
## Within R2 0.20416 0.20843
## need.reg11
## Dependent Var.: primaryADL
##
## gender -0.0537* (0.0185)
## age 0.0145* (0.0046)
## age square -0.0002* (4.02e-5)
## edu
## working -0.0108 (0.0083)
## unmarried -0.0529* (0.0141)
## SubSameSex 0.0586* (0.0198)
## livTogether 0.2777*** (0.0048)
## subject_in_nursing_house -0.0257 (0.0197)
## subject_residency10 0.0825** (0.0137)
## subject_residency11 -0.0356 (0.0218)
## subject_residency12 -0.0307. (0.0115)
## subject_residency13 0.0103 (0.0411)
## subject_residency14 0.0236 (0.0116)
## subject_residency15 -0.0011 (0.0178)
## subject_residency16 -0.0084 (0.0245)
## subject_residency17 0.0233* (0.0067)
## subject_residency18 -0.0355 (0.0295)
## subject_residency19 -0.0307* (0.0067)
## subject_residency2 -0.0307 (0.0177)
## subject_residency20 0.0264 (0.0374)
## subject_residency21 -0.0481 (0.0279)
## subject_residency22 0.0025 (0.0342)
## subject_residency3 0.0060 (0.0225)
## subject_residency4 -0.0597 (0.0723)
## subject_residency5 0.0215 (0.0287)
## subject_residency6 0.0664 (0.0522)
## subject_residency7 0.0109 (0.0131)
## subject_residency8 -0.0150* (0.0035)
## subject_residency9 -0.0295 (0.0177)
## attend_at_least_high_school
## attend_at_least_uni -0.0692** (0.0091)
## Fixed-Effects: ------------------
## survey_year Yes
## ___________________________ __________________
## S.E.: Clustered by: survey_year
## Observations 3,456
## R2 0.20828
## Within R2 0.20820Decision Tree
simple.tree <- rpart(primaryADL ~ gender + age + age**2 +
edu + working +
unmarried + livTogether, data = fm.with.need, cp=.008)rpart.plot(simple.tree, faclen=0,
box.palette="RdBu",
fallen.leaves=TRUE,
shadow.col="gray",
nn=TRUE)
simple.tree <- rpart(primaryADL ~ gender + age + age**2 +
edu + working + SubSameSex +
unmarried, data = fm.with.need, cp=.003)
rpart.plot(simple.tree, faclen=0,
box.palette="RdBu",
fallen.leaves=TRUE,
shadow.col="gray",
nn=TRUE)
simple.tree <- rpart(primaryADL ~ gender + age + age**2 +
attend_at_least_uni + attend_at_least_high_school + working + SubSameSex +
unmarried, data = fm.with.need, cp=.003)
rpart.plot(simple.tree, faclen=0,
box.palette="RdBu",
fallen.leaves=TRUE,
shadow.col="gray",
nn=TRUE)
PCA
data.pca <- fm.with.need[,c("gender", "age", "edu", "working",
"unmarried", "SubSameSex", "primaryADL")]
data.pca$primaryADL <- factor(data.pca$primaryADL)
simple.pca <- prcomp(formula = ~ .,
data = data.pca[,1:6],
scale = TRUE) plot(simple.pca, type="line")
abline(h=1, col="blue")
simple.pca$rotation[,1:3]## PC1 PC2 PC3
## gender -0.4514577 0.4527224 -0.23430113
## age 0.3896267 0.5306502 0.02055758
## edu -0.4706090 -0.1923960 0.34688539
## working -0.4409099 0.1265690 0.59644448
## unmarried -0.2862820 -0.4933359 -0.55438207
## SubSameSex 0.3828123 -0.4658718 0.40157862first.pca <- simple.pca$rotation[, 1] # 第一主成份
second.pca <- simple.pca$rotation[, 2] # 第二主成份
third.pca <- simple.pca$rotation[, 3] # 第三主成份
dotchart(first.pca[order(first.pca, decreasing=FALSE)] , # 排序後的係數
main="Loading Plot for PC1", # 主標題
xlab="Variable Loadings", # x軸的標題
col="black")
dotchart(second.pca[order(second.pca, decreasing=FALSE)] , # 排序後的係數
main="Loading Plot for PC2", # 主標題
xlab="Variable Loadings", # x軸的標題
col="black")
dotchart(third.pca[order(third.pca, decreasing=FALSE)] , # 排序後的係數
main="Loading Plot for PC3", # 主標題
xlab="Variable Loadings", # x軸的標題
col="black")
# !!
autoplot(simple.pca, data = data.pca, colour = 'primaryADL', alpha=0.1, loadings = TRUE, loadings.colour = 'gray', loadings.label = TRUE, loadings.label.alpha = 0.4, loadings.label.colour = "black")## Warning in as.data.table.list(x, keep.rownames = keep.rownames, check.names =
## check.names, : Item 2 has 3461 rows but longest item has 3713; recycled with
## remainder.